We demonstrate how an artificial agent’s conversational style can be adapted to different interlocutors by using a model of Person Memory. While other approaches so far rely on adapting an agent’s behavior according to one particular factor like personality or relationship, we show how to enable an agent to take diverse factors into account at once by exploiting social categories. This way, our...

In this paper we overviews the ongoing project that we called POPSICLE (Patterns in Orientation: Pattern-Aided Simulated Interaction Context Learning Experiment). We overview the experimental setup, and give some preliminary results.

Building an intelligent agent, which simulates human-level learning appropriate for learning math, science, or a second language, could potentially benefit both education in understanding human learning, and artificial intelligence in creating human-level intelligence. Recently, we have proposed an efficient approach to acquiring procedural knowledge using transfer learning. However, it operate...

The oil droplet is used as a simple model system to study the physical basis of intelligence. The oil droplet is a structure produced by self-assembly. By coupling a chemical reaction in the oil droplet with a physical instability, the droplet displays lifelike properties such as autonomous motility, sensory-motor coupling, gradient following and agent-to-agent signaling. By developing this sys...

The concept embodying agent-mediated personal knowledge management (PKM) manifests a bottom-up process of organisational knowledge management (OKM) in achieving collective goals. Exploiting this concept from the perspective of crossing organisational boundaries and into the realm of social network, the concept of social intelligence is proposed. Social intelligence has been defined in many aspe...

Rapid advancements of both microsystem technology and multi-agent systems have generated a new discipline, arising from the fusion of microrobotics technologies and of swarm intelligence theories. Microrobotics contributes with new capabilities in manipulating objects in the microscale and in developing miniaturized intelligent machines, while swarm intelligence supplies new algorithms allowing...

We have defined the Cassiopeia method, whose specificity is to focus the analysis and design of a multiagent system on the notion of organization. This article reports the use of this methodological framework for designing and implementing the organization of a robot soccer team in the context of a research project on collective robotics. We show why we chose this application, and we discuss it...

In this paper we present a test bed for multiagent control systems in road traffic management. As the complexity of traffic control on a network grows it becomes more difficult to coordinate the actions of the large number of heterogeneous traffic management instruments that are available in the network. One way of handling this complexity is to divide the coordination problem into smaller cohe...

Motivation: In the last decade there has been a surge of interest within the finance community in describing equity markets through computational agent models [7]. At the same time, financial markets are an important application area within artificial intelligence for the fields of agent-based modeling and machine learning, since agent objectives and interactions tend to be more clearly defined...